<?xml version="1.0" encoding="UTF-8"?>
<doi_batch version="4.3.0" xmlns="http://www.crossref.org/doi_resources_schema/4.3.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.crossref.org/doi_resources_schema/4.3.0 http://www.crossref.org/schema/deposit/doi_resources4.3.0.xsd">
<head>
<doi_batch_id>51608b25-40bf-4826-9a17-fa4ba1fa6a91</doi_batch_id>
<depositor>
<name>beie</name>
<email_address>director@blueeyesintelligence.org</email_address>
</depositor>
</head>
<body>
<doi_citations>
<doi>10.35940/ijitee.K9503.09101121</doi>
<citation_list><citation key="ref0"><doi>10.1016/j.is.2020.101565</doi><unstructured_citation>Papadakis, G. Mandilaras, L. Gagliardelli, G. Simonini, E. Thanos, G. Giannakopoulos, S. Bergamaschi, T. Palpanas And M. Koubarakis, &quot;Three-Dimensional Entity Resolution With Jedai,&quot; Elsevier, Vol. 93, 29 May 2020.</unstructured_citation></citation><citation key="ref1"><doi>10.1145/2064085.2064087</doi><unstructured_citation>L. Kolb, H. Köpcke, A. Thor And E. Rahm, &quot;Learning-Based Entity Resolution With Mapreduce,&quot; In Clouddb, 2011.</unstructured_citation></citation><citation key="ref2"><doi>10.1088/1742-6596/978/1/012118</doi><unstructured_citation>Gunawan, M. S. Lubis, D. Arisandi And B. Azzahry, &quot;Data Pre-Processing In Record Linkage To Find The Same Companies From Companies From Different Databases,&quot; 2nd International Conference On Computing And Applied Informatics, Vol. 978, 2017.</unstructured_citation></citation><citation key="ref3"><doi>10.1109/ICENCO.2017.8289792</doi><unstructured_citation>R. M. Abd El-Ghafar, M. H. Gheith, A. H. El-Bastawissy And E. S. Nasr, &quot;Record Linkage Approaches In Big Data: A State Of A State Of Art Study,&quot; In 13th International Computer Engineering Conference (Icenco), Cairo, 2017.</unstructured_citation></citation><citation key="ref4"><unstructured_citation>W. W. Cohen, P. Ravikumar And S. E. Fienberg, &quot;A Comparison Of String Distance Metrics For Name-Matching Tasks,&quot; International Joint Conference On Artificial Intelligence, P. 73-78, 2003.</unstructured_citation></citation><citation key="ref5"><unstructured_citation>J. Mielke, &quot;A Phonetically-Based Phonetic Similarity Metric,&quot; In Nels, 2009.</unstructured_citation></citation><citation key="ref6"><doi>10.1016/j.jss.2017.03.003</doi><unstructured_citation>G. Mestre, C. E. S. Pires, D. C. Nascimento, A. R. Queiroz, V. B. Santos And T. B. Araujoa, &quot;An Efficient Spark-Based Adaptive Windowing For Entity Matching,&quot; Journal Of Systems And Software, Vol. 128, P. 1:10, 3 March 2017.</unstructured_citation></citation><citation key="ref7"><doi>10.1109/HPCS.2018.00138</doi><unstructured_citation>Simonini, L. Gagliardelli, S. Zhu And S. Bergamaschi, &quot;Enhancing Loosely Schema-Aware Entity Resolution With User Interaction,&quot; Hpcs, P. 860-864, July 2018.</unstructured_citation></citation><citation key="ref8"><doi>10.14778/2994509.2994533</doi><unstructured_citation>Simonini, S. Bergamaschi And H. V. Jagadish, &quot;Blast: A Loosely Schema-Aware Meta-Blocking Approach For Entity Resolution,&quot; In Pvldb, 2016.</unstructured_citation></citation><citation key="ref9"><unstructured_citation>R. Pita, C. Pinto, P. Melo, M. Silva, M. Barreto And D. Rasella, &quot;A Spark-Based Workflow For Probabilistic Record Linkage Of Healthcare Data,&quot; In Edbt/Icdt Workshops, 2015.</unstructured_citation></citation><citation key="ref10"><doi>10.12783/dtetr/ecame2017/18462</doi><unstructured_citation>M.-G. Chen And H.-J. Sui, &quot;Parallel Entity Resolution With Apache Spark,&quot; In International Conference On Electronic, Control, Automation And Mechanical Engineering (Ecame 2017) , 2018.</unstructured_citation></citation><citation key="ref11"><unstructured_citation>Wang And S. Karimi, &quot;Parallel Duplicate Detection In Adverse Drug Reaction Databases With Spark,&quot; In 19th International Conference On Extending Database Technology, Bordeaux, France, 2016.</unstructured_citation></citation><citation key="ref12"><unstructured_citation>B. Gatius And R. G. González, &quot;Deduplication Of Universitat De Lleida Scholarly Data,&quot; 2017.</unstructured_citation></citation><citation key="ref13"><doi>10.1088/1742-6596/1743/1/012005</doi><unstructured_citation>Alami, Y. Aassem And I. Hafidi, &quot;Kf-Swoosh: An Efficient Spark-Based Entity Resolution Algorithm For Bigdata,&quot; Journal Of Physics: Conference Series, 2021.</unstructured_citation></citation><citation key="ref14"><unstructured_citation>Martinez, S. Cristobal And S. Belkoura, &quot;Smart Data Fusion: Probabilistic Record Linkage Adapted To Merge Two Trajectories From Different Sources,&quot; In Eighth Sesar Innovation Days, 2018.</unstructured_citation></citation><citation key="ref15"><unstructured_citation>L. Gagliardelli, G. Simonini, D. Beneventano And S. Bergamaschi, &quot;Sparkr: Scaling R Programs With Spark,&quot; In 22nd International Conference On Extending Database Technology (Edbt), Lisbon, Portugal, 2019.</unstructured_citation></citation><citation key="ref16"><unstructured_citation>L. Gagliardelli, S. Zhu, G. Simonini And S. Bergamaschi, &quot;Bigdedup: A Big Data Integration Toolkit For Duplicate Detection In Industrial Scenarios,&quot; In Proc. Int. Conf. On Transdisciplinary Engineering (Te2018), 2018.</unstructured_citation></citation><citation key="ref17"><doi>10.1109/TKDE.2013.54</doi><unstructured_citation>Papadakis, G. Koutrika, T. Palpanas And W. Nejdl, &quot;Meta-Blocking: Taking Entity Resolution To The Next Level,&quot; Ieee Transactions On Knowledge And Data Engineering, Vol. 26, No. 8, P. 1964:1960, August 2014.</unstructured_citation></citation><citation key="ref18"><doi>10.1016/j.is.2020.101565</doi><unstructured_citation>Papadakis, G. Mandilaras, L. Gagliardelli, G. Simonini, E. Thanos, G. Giannakopoulos, S. Bergamaschi, T. Palpanas And M. Koubarakis, &quot;Three-Dimensional Entity Resolution With Jedai,&quot; Elsevier, 29 May 2020.</unstructured_citation></citation><citation key="ref19"><doi>10.1145/2882903.2903737</doi><unstructured_citation>T. Sagi, A. Gal, O. Barkol, R. Bergman And A. Avram, &quot;Multi-Source Uncertain Entity Resolution: Transforming Holocaust Victim Reports Into People,&quot; In International Conference On Management Of Data, 2016.</unstructured_citation></citation><citation key="ref20"><doi>10.1049/PBPC035F_ch13</doi><unstructured_citation>Karakasidis And G. Koloniari, &quot;Private Entity Resolution For Big Data On Apache Spark Using Multiple Phonetic Codes,&quot; Big Data Recommender Systems, Vol. 1, 2019.</unstructured_citation></citation><citation key="ref21"><doi>10.2196/preprints.18920</doi><unstructured_citation>P. Brown And S. M. Randall, &quot;Secure Record Linkage Of Large Health Data Sets: Evaluation Of A Hybrid Cloud Model,&quot; Jmir Medical Informatics, Vol. 8, No. 7, 2020.</unstructured_citation></citation><citation key="ref22"><doi>10.1109/JBHI.2018.2796941</doi><unstructured_citation>Pita, C. Pinto, S. Sena And R. Fiaccone, &quot;On The Accuracy And Scalability Of Probabilistic Data Linkage Over The Brazilian 114 Million Cohort,&quot; Ieee J Biomed Health Inform, Vol. 22, No. 2, P. 346-353, 2018.</unstructured_citation></citation><citation key="ref23"><doi>10.1007/978-3-319-99987-6_1</doi><unstructured_citation>X. Chen, R. Zoun, E. Schallehn, S. Mantha, K. Rapuru And G. Saake, &quot;Exploring Spark-Sql-Based Entity Resolution Using The Persistence Capability,&quot; In International Conference: Beyond Databases, Architectures And Structures, Cham, 2018.</unstructured_citation></citation><citation key="ref24"><unstructured_citation>Manyika, M. Chui, B. Brown, J. Bughin, R. Dobbs, C. Roxburgh And A. H. Byers, &quot;Big Data: The Next Frontier For Innovation, Competition, And Productivity.,&quot; 9 July 2012. [Online]. Available: Http://Www.Mckinsey.Com/Insights/Mgi/Research/Technology_And_Innovation/Big_Data_The_ Next_Frontier_For_Innovation.</unstructured_citation></citation><citation key="ref25"><doi>10.1016/j.ins.2014.01.015</doi><unstructured_citation>P. Chen And C.-Y. Zhang, &quot;Data-Intensive Applications, Challenges, Techniques And Technologies: A Survey On Big Data,&quot; Information Sciences, Vol. 275, P. 314:347, 2014.</unstructured_citation></citation><citation key="ref26"><unstructured_citation>Sorzano, J. Vargas And A. P. Montano, &quot;A Survey Of Dimensionality Reduction Techniques,&quot; Arxiv:1403.2877, 2014.</unstructured_citation></citation><citation key="ref27"><doi>10.1007/978-1-4614-6849-3</doi><unstructured_citation>M. Kuhn And K. Johnson, Applied Predictive Modeling., Springer, 2013, P. 488.</unstructured_citation></citation><citation key="ref28"><unstructured_citation>K.-T. Huang, Y. W. Lee And R. Y. Wang, Quality Information And Knowledge, New Jersey: Prentice Hall, 1999, Pp. 25-29.</unstructured_citation></citation><citation key="ref29"><doi>10.1287/mnsc.31.2.150</doi><unstructured_citation>P. Ballou And H. L. Pazer, &quot;Modeling Data And Process Quality In Multiinput, Multi-Output Information Systems,&quot; Management Science, Vol. 31, No. 2, Pp. 150-162, 1985.</unstructured_citation></citation><citation key="ref30"><doi>10.1145/27544.27546</doi><unstructured_citation>P. Ballou, H. L. Pazer, S. Belardo And B. Klein, &quot;Implications Of Data Quality For Spreadsheet Analysis,&quot; Acm Sigmis Database: The Database For Advances In Information Systems, Vol. 18, No. 3, Pp. 13-19, March 1987.</unstructured_citation></citation><citation key="ref31"><doi>10.1186/1472-6947-2-9</doi><unstructured_citation>T. Churches, P. Christen, K. Lim And J. X. Zhu, &quot;Preparation Of Name And Address Data For Record Linkage Using Hidden Markov Models,&quot; Bmc Medical Informatics And Decision Making , 2002.</unstructured_citation></citation><citation key="ref32"><doi>10.1186/s41044-016-0014-0</doi><unstructured_citation>S. García, S. Ramírez-Gallego, J. Luengo, J. M. Benítez And F. Herrera, &quot;Big Data Preprocessing: Methods And Prospects,&quot; Big Data Analytics, November 2016.</unstructured_citation></citation><citation key="ref33"><doi>10.1088/1742-6596/978/1/012118</doi><unstructured_citation>D. Gunawan, M. S. Lubis, D. Arisandi And B. Azzahry, &quot;Data Pre-Processing In Record Linkage To Find The Same Companies From Different Databases,&quot; Journal Of Physics: Conference Series, 2018.</unstructured_citation></citation><citation key="ref34"><unstructured_citation>S. Loeb , P. Morris, S. Dynarski , S. Reardon , D. Mcfarland And S. Reber, &quot;Descriptive Analysis In Education: A Guide For Researchers,&quot; Ncee, Washington, 2017.</unstructured_citation></citation><citation key="ref35"><doi>10.1109/TKDE.2012.150</doi><unstructured_citation>Papadakis, E. Ioannou, T. Palpanas, C. Niede And W. Nejdl, &quot;A Blocking Framework For Entity Resolution In Highly Heterogeneous Information Spaces,&quot; Ieee Transactions On Knowledge And Data Engineering, Vol. 25, No. 12, Pp. 2665-2682, December 2013.</unstructured_citation></citation><citation key="ref36"><doi>10.1016/j.is.2012.11.008</doi><unstructured_citation>Kenig And A. Gal, &quot;Mfiblocks: An Effective Blocking Algorithm For Entity Resolution,&quot; Information Systems, Vol. 38, No. 6, Pp. 908-926, 2013.</unstructured_citation></citation><citation key="ref37"><doi>10.35940/ijitee.I7070.079920</doi><unstructured_citation>R. M. Abd El-Ghafar, A. H. El-Bastawissy, E. S. Nasr And M. H. Gheith, &quot;An Efficient Multi-Phase Blocking Strategy For Entity Resolution In Big Data,&quot; International Journal Of Innovative Technology And Exploring Engineering (Ijitee), Vol. 9, No. 9, Pp. 254-263, July 2020.</unstructured_citation></citation><citation key="ref38"><doi>10.1145/3377455</doi><unstructured_citation>Papadakis, D. Skoutas, E. Thanos And T. Palpanas, &quot;A Servay Of Blocking And Filtering Techniques For Entity Resolution,&quot; Association For Computing Machinery (Acm), 2019.</unstructured_citation></citation><citation key="ref39"><unstructured_citation>Skoutas , T. Vergoulis, K. Patroumpas, S. Chatzopoulos, A. Zeakis , G. Chatzigeorgakidis, L. Shimomura , N. Yakovets, G. Fletcher, H. Shahrivari , O. Papapetrou And T. Spinner, &quot;Similarity Search, Entity Resolution,&quot; Horizon 2020, 2020.</unstructured_citation></citation><citation key="ref40"><unstructured_citation>Wang, H. T. Shen, J. S. Song And J. Ji, &quot;Hashing For Similarity Search: A Survey,&quot; Corr, 2014.</unstructured_citation></citation><citation key="ref41"><unstructured_citation>Y. W. Yu And W. M. Griffin, &quot;Hyperminhash: Minhash In Loglog Space,&quot; Journal Of Latex Class Files , 2019.</unstructured_citation></citation><citation key="ref42"><unstructured_citation>M. Pham And T. L. X. Vu, &quot;Elodu: Entity Resolution In Big Data,&quot; Worcester Polytechnic Institute, 2015.</unstructured_citation></citation><citation key="ref43"><doi>10.1016/j.procs.2016.05.218</doi><unstructured_citation>S. P. Benny, S. V. And P. A. , &quot;Hadoop Framework For Entity Resolution Within High Velocity Streams,&quot; In International Conference On Computational Modeling And Security (Cms), 2016.</unstructured_citation></citation><citation key="ref44"><unstructured_citation>J. Feigenbaum, &quot;A Machine Learning Approach To Census Record Linking,&quot; 2016.</unstructured_citation></citation><citation key="ref45"><doi>10.1016/j.procs.2018.05.169</doi><unstructured_citation>P. Dahiya And D. K. Srivastava, &quot;Network Intrusion Detection In Big Dataset Using Spark,&quot; In International Conference On Computational Intelligence And Data Science, 2018.</unstructured_citation></citation><citation key="ref46"><unstructured_citation>Moir And J. Dean, &quot;A Machine Learning Approach To Generic Entity Resolution In Support Of Cyber Situation Awareness,&quot; In Proceedings Of The 38th Australasian Computer Science Conference (Acsc 2015), 2015.</unstructured_citation></citation><citation key="ref47"><doi>10.1145/2951894.2951896</doi><unstructured_citation>C.-J. Schild, S. Schultz And F. Wieser, &quot;Linking Deutsche Bundesbank Company Data Using Machine-Learning-Based Classification,&quot; Deutsche Bundesbank Research Data And Service Centre, 2017.</unstructured_citation></citation><citation key="ref48"><doi>10.3233/IDA-2007-11602</doi><unstructured_citation>Omran, A. A. Salman And A. Engelbrecht, &quot;An Overview Of Clustering Methods,&quot; Intelligent Data Analysis, Vol. 11, No. 6, Pp. 583-605, 2007.</unstructured_citation></citation><citation key="ref49"><doi>10.1007/978-1-4899-7993-3_2547-2</doi><unstructured_citation>X. L. Dong And D. Srivastava, &quot;Entity Resolution,&quot; Encyclopedia Of Database Systems, 2016.</unstructured_citation></citation><citation key="ref50"><doi>10.1016/S0377-2217(02)00730-0</doi><unstructured_citation>Meyer, H. Naessens And B. D. Baets, &quot;Algorithms For Computing The Min-Transitive Closure And Associated Partition Tree Of A Symmetric Fuzzy Relation,&quot; European Journal Of Operational Research, Vol. 155, No. 1, Pp. 226-238, 2004.</unstructured_citation></citation><citation key="ref51"><unstructured_citation>B. Li, Entity Resolution Over Graphs, Australia, 2014.</unstructured_citation></citation><citation key="ref52"><doi>10.1007/978-3-319-69459-7_25</doi><unstructured_citation>Nentwig, A. Groß, M. Moller And E. Rahm, &quot;Distributed Holistic Clustering On Linked Data,&quot; In On The Move To Meaningful Internet Systems. Otm 2017 Conferences, 2017.</unstructured_citation></citation><citation key="ref53"><unstructured_citation>B. C And B. B. P. M, &quot;Data Linkage For Big Data Using Hadoop Mapreduce,&quot; In Ijcst, 2015.</unstructured_citation></citation><citation key="ref54"><unstructured_citation>Kejriwal, &quot;Entity Resolution In A Big Data Framework,&quot; In Twenty-Ninth Aaai Conference On Artificial Intelligence, Austin, Texas, 2015.</unstructured_citation></citation><citation key="ref55"><unstructured_citation>Efthymiou, K. Stefanidis And V. Christophides, &quot;Minoan Er: Progressive Entity Resolution In The Web Of Data,&quot; In 19th International Conference On Extending Database Technology, Edbt, Bordeaux, France, 2016.</unstructured_citation></citation><citation key="ref56"><unstructured_citation>&quot;Sparker: Scaling Entity Resolution In Spark,&quot; In 22nd International Conference On Extending Database Technology (Edbt), Lisbon, Portugal, 2019.</unstructured_citation></citation><citation key="ref57"><unstructured_citation>&quot;Bigdedup: A Big Data Integration Toolkit For Duplicate Detection In Industrial Scenarios,&quot; In Proc. Int. Conf. On Transdisciplinary Engineering (Te2018), 2018.</unstructured_citation></citation><citation key="ref58"><doi>10.7250/csimq.2018-16.04</doi><unstructured_citation>Saeedi, M. Nentwig, E. Peukert And E. Rahm, &quot;Scalable Matching And Clustering Of Entities With Famer,&quot; Complex Systems Informatics And Modeling Quarterly (Csimq), No. 16, P. 61-83, September/October 2018.</unstructured_citation></citation><citation key="ref59"><doi>10.3844/jcssp.2011.341.347</doi><unstructured_citation>M. Ektefa, F. Sidi, H. Ibrahim, M. A. Jabar And S. Memar, &quot;A Comparative Study In Classification Techniques For Unsupervised Record Linkage Model,&quot; Journal Of Computer Science, Vol. 7, No. 3, Pp. 341-347, 2011.</unstructured_citation></citation><citation key="ref60"><doi>10.1007/978-3-030-01872-6_3</doi><unstructured_citation>Jurek-Loughrey And D. P, Semi-Supervised And Unsupervised Approaches To Record Pairs Classification In Multi-Source Data Linkage, Switzerland: Springer, 2019.</unstructured_citation></citation><citation key="ref61"><unstructured_citation>M. Michalowski, S. Thakkar And C. A. Knoblock, &quot;Exploiting Secondary Sources For Unsupervised Record Linkage,&quot; In Proceedings Of The 30th Vldb Conference, Canada,, 2004.</unstructured_citation></citation><citation key="ref62"><unstructured_citation>S. Sheth And A. R. Deshpande, &quot;A Decision Tree Based Record Linkage For Recommendation Systems,&quot; International Journal Of Engineering Research And General Science ,, Vol. 3, No. 4, 2015.</unstructured_citation></citation><citation key="ref63"><doi>10.1145/3132847.3132949</doi><unstructured_citation>K. Qian, L. Popa And P. Sen, &quot;Active Learning For Large-Scale Entity Resolution,&quot; In Cikm, New York, 2017.</unstructured_citation></citation></citation_list>
</doi_citations>
</body>
</doi_batch>
